GPU Technology Conference—NVIDIA today announced a collaboration with Amazon Web Services (AWS) IoT on NVIDIA® Jetson™ to enable customers to deploy AI and deep learning to millions of connected devices.
This joint solution enables models to be easily created, trained and optimized on AWS, then deployed to Jetson-powered edge devices using AWS IoT Greengrass.
The NVIDIA Jetson platform offers AI at the edge with high-performance and power-efficient computing. Applications include autonomous machines and smart cameras for industries such as retail, manufacturing, agriculture and more.
AWS IoT Greengrass seamlessly extends AWS to edge devices, including machine learning inference, so they can act locally on the data they generate while still using the cloud for management, analytics and durable storage. Jetson-powered devices perform inference at the edge to take near real-time action using AWS IoT Greengrass. Data is then sent back to machine learning services such as Amazon SageMaker to improve model accuracy.
Jetson comes with a comprehensive set of software tools and SDKs, including NVIDIA JetPack™. It also supports multiple frameworks such as MXNet, Caffe, TensorFlow and PyTorch, so developers can use these algorithms to quickly deploy real-world applications.
“Jetson is a high-performance computer that’s built on the same architecture and unified software that powers the world’s fastest supercomputers,” said Deepu Talla, vice president and general manager of Autonomous Machines at NVIDIA. “We offer the new Jetson Nano all the way to Jetson AGX Xavier, so IoT devices can now scale from small IoT devices to powerful IoT gateways.”
Jetson and AWS IoT Greengrass make it easy to deploy machine learning models optimized to run on IoT devices. Customers can save bandwidth and cost by running near real-time inference directly on a Jetson-powered device instead of sending data to the cloud first.
A Variety of Use Cases Made Smarter
Jetson brings AI to applications that were once unimaginable. In high-precision agriculture, Jetson-powered cameras running AWS IoT Greengrass can target weeds in near real time, capture previously unidentified weeds, upload anomalies to the cloud, and retrain and deploy the model quickly. This powerful technology combination makes agriculture smarter and more efficient to help feed the world’s growing population.
For automated optical inspection, product defects can be quickly identified on factory floors to avoid delays on manufacturing assembly lines. This increases productivity and minimizes losses to improve overall operational efficiency.
In retail, Jetson-powered devices can monitor inventory, customer behavior, and checkout and process data on the edge, using AWS IoT Greengrass to deploy trained neural networks. This brings operational efficiencies and scale to the retail industry.
AWS will be showcasing a variety of IoT, machine learning and robotics demonstrations powered by Jetson devices at NVIDIA GTC this week. Stop by AWS booth 1221 or the Jetson pavilion 1543 and 1545 to see AWS IoT Greengrass and Jetson in action.